Monday, June 13, 2016

There's Good Science, Bad Science and Evil Science

How a liberal bias is killing science
Remember when a study came out that said that conservative political beliefs are associated with psychotic traits, such as authoritarianism and tough-mindedness? While liberalism is associated with "social desirability?"

The American Journal of Political Science recently had to print a somewhat embarrassing correction, as the invaluable website Retraction Watch pointed out: It turns out somebody made an Excel error. And the study's results aren't a little off. They aren't a lot off. They are exactly backwards.

Writes the American Journal of Political Science:
The interpretation of the coding of the political attitude items in the descriptive and preliminary analyses portion of the manuscript was exactly reversed. Thus, where we indicated that higher scores in Table 1 (page 40) reflect a more conservative response, they actually reflect a more liberal response. [American Journal of Political Science]
In other words, at least according to this study, it's liberals who are psychotic and conservatives who are awesome.

Well, obviously, as a conservative, I first had to stop laughing for 10 minutes before I could catch my breath.

I could also make a crassly political point, like of course liberals are psychotic given liberal authoritarianism, and of course conservatives are more balanced — after all, we're happier and we have better sex.

But actually, this is bigger than that. Adds Retraction Watch, "That 2012 paper has been cited 45 times, according to Thomson Reuters Web of Science."
. . .
Contacted by Retraction Watch, the authors of the study hem and haw and say that their point was not about conservatives or liberals, but about the magnitude of differences between those camps.

Yeah, right.
At a bare minimum, the science was bad because they didn't understand the direction of their own coding of the data, and they when they found effects, they just leaped to the conclusion they were looking for in the first place before checking it against the data.

This is "Political science", not really a science at all, merely politics pretending to be science adopting it's name, but not it's strictures. In fact, it's a pretty good indication that it's not a science if they have to use the word "science" in the name. Physics, biology, chemistry, medicine, all sciences. Political science, social science, environmental science, health science all not really science. I'm not the first to notice that, but I can't remember who made it first.

No comments:

Post a Comment